agentleFS
Sign inStart free
SrltasSrltas/claude-skills/CLAUDE.md

claude-skills

CLAUDE.md0 starsChanged 12 days agoMITView on GitHub

A git-managed collection of Claude Code skills, focused on CUBRID migration, JDBC, and Hibernate work. just install links each skill into ~/.claude/skills/, so edits here take effect without reinstalling. Each top-level directory containing a SKILL.md is one skill. Skills are grouped by domain prefix: Prefer the skill-create skill, which scaffolds and self-reviews a new SKILL.md. Manually: vimkim/my-cubrid-skills (cloned locally at ../my-cubrid-skills) is a separate collection by another engineer, focused on CUBRID engine (C/C++) development. Use it as read-only inspiration only:…

The file

We split this CLAUDE.md into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Prefer the skill-create skill, which scaffolds and self-reviews a new SKILL.md.

    line 17
  2. Very specific:

    Create <prefix>-<name>/SKILL.md with frontmatter (name, description) and numbered steps, and add its row to the README Skills table.

    line 19
  3. Distinctive:

    Commit the new directory.

    line 22

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
CLAUDE.md

claude-skills

A git-managed collection of Claude Code skills, focused on CUBRID migration, JDBC, and Hibernate work. just install links each skill into ~/.claude/skills/, so edits here take effect without reinstalling.

Directory structure

Each top-level directory containing a SKILL.md is one skill. Skills are grouped by domain prefix:

  • hhh-*: Hibernate ORM upstream / dialect work
  • cmt-*: CUBRID Migration Toolkit (runs, schema/data parity)
  • jdbc-*: CUBRID JDBC driver
  • cubrid-*: General CUBRID (e.g. manual lookup)
  • (no prefix): truly general-purpose skills

Adding / updating a skill

Prefer the skill-create skill, which scaffolds and self-reviews a new SKILL.md. Manually:

  1. Create <prefix>-<name>/SKILL.md with frontmatter (name, description) and numbered steps, and add its row to the README Skills table.
  2. just install to link it (needed once per new skill).
  3. just check must pass.
  4. Commit the new directory.

Reference material (read-only)

vimkim/my-cubrid-skills (cloned locally at ../my-cubrid-skills) is a separate collection by another engineer, focused on CUBRID engine (C/C++) development. Use it as read-only inspiration only: never modify, fork, install from, or push to it. Every skill here is written fresh.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free